| |
| |
Complete Table of Contents | |
| |
| |
Acknowledgments | |
| |
| |
List of Figures | |
| |
| |
List of Algorithms | |
| |
| |
List of Boxes | |
| |
| |
| |
Introduction | |
| |
| |
| |
Motivation | |
| |
| |
| |
Structured Probabilistic Models | |
| |
| |
| |
Overview and Roadmap | |
| |
| |
| |
Historical Notes | |
| |
| |
| |
Foundations | |
| |
| |
| |
Probability Theory | |
| |
| |
| |
Graphs | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Representation | |
| |
| |
| |
The Bayesian Network Representation | |
| |
| |
| |
Exploiting Independence Properties | |
| |
| |
| |
Bayesian Networks | |
| |
| |
| |
Independencies in Graphs | |
| |
| |
| |
From Distributions to Graphs | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Undirected Graphical Models | |
| |
| |
| |
The Misconception Example | |
| |
| |
| |
Parameterization | |
| |
| |
| |
Markov Network Independencies | |
| |
| |
| |
Parameterization Revisited | |
| |
| |
| |
Bayesian Networks and Markov Networks | |
| |
| |
| |
Partially Directed Models | |
| |
| |
| |
Summary and Discussion | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Local Probabilistic Models | |
| |
| |
| |
Tabular CPDs | |
| |
| |
| |
Deterministic CPDs | |
| |
| |
| |
Context-Specific CPDs | |
| |
| |
| |
Independence of Causal Influence | |
| |
| |
| |
Continuous Variables | |
| |
| |
| |
Conditional Bayesian Networks | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Template-Based Representations | |
| |
| |
| |
Introduction | |
| |
| |
| |
Temporal Models | |
| |
| |
| |
Template Variables and Template Factors | |
| |
| |
| |
Directed Probabilistic Models for Object-Relational Domains | |
| |
| |
| |
Undirected Representation | |
| |
| |
| |
Structural Uncertainty | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Gaussian Network Models | |
| |
| |
| |
Multivariate Gaussians | |
| |
| |
| |
Gaussian Bayesian Networks | |
| |
| |
| |
Gaussian Markov Random Fields | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
The Exponential Family | |
| |
| |
| |
Introduction | |
| |
| |
| |
Exponential Families | |
| |
| |
| |
Factored Exponential Families | |
| |
| |
| |
Entropy and Relative Entropy | |
| |
| |
| |
Projections | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Inference | |
| |
| |
| |
Exact Inference: Variable Elimination | |
| |
| |
| |
Analysis of Complexity | |
| |
| |
| |
Variable Elimination: The Basic Ideas | |
| |
| |
| |
Variable Elimination | |
| |
| |
| |
Complexity and Graph Structure: Variable Elimination | |
| |
| |
| |
Conditioning | |
| |
| |
| |
Inference with Structured CPDs | |
| |
| |
| |
Summary and Discussion | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Exact Inference: Clique Trees | |
| |
| |
| |
Variable Elimination and Clique Trees | |
| |
| |
| |
Message Passing: Sum Product | |
| |
| |
| |
Message Passing: Belief Update | |
| |
| |
| |
Constructing a Clique Tree | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Inference as Optimization | |
| |
| |
| |
Introduction | |
| |
| |
| |
Exact Inference as Optimization | |
| |
| |
| |
Propagation-Based Approximation | |
| |
| |
| |
Propagation with Approximate Messages | |
| |
| |
| |
Structured Variational Approximations | |
| |
| |
| |
Summary and Discussion | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Particle-Based Approximate Inference | |
| |
| |
| |
Forward Sampling | |
| |
| |
| |
Likelihood Weighting and Importance Sampling | |
| |
| |
| |
Markov Chain Monte Carlo Methods | |
| |
| |
| |
Collapsed Particles | |
| |
| |
| |
Deterministic Search Methods | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
MAP Inference | |
| |
| |
| |
Overview | |
| |
| |
| |
Variable Elimination for (Marginal) MAP | |
| |
| |
| |
Max-Product in Clique Trees | |
| |
| |
| |
Max-Product Belief Propagation in Loopy Cluster Graphs | |
| |
| |
| |
MAP as a Linear Optimization Problem | |
| |
| |
| |
Using Graph Cuts for MAP | |
| |
| |
| |
Local Search Algorithms | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Inference in Hybrid Networks | |
| |
| |
| |
Introduction | |
| |
| |
| |
Variable Elimination in Gaussian Networks | |
| |
| |
| |
Hybrid Networks | |
| |
| |
| |
Nonlinear Dependencies | |
| |
| |
| |
Particle-Based Approximation Methods | |
| |
| |
| |
Summary and Discussion | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Inference in Temporal Models | |
| |
| |
| |
Inference Tasks | |
| |
| |
| |
Exact Inference | |
| |
| |
| |
Approximate Inference | |
| |
| |
| |
Hybrid DBNs | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Learning | |
| |
| |
| |
Learning Graphical Models: Overview | |
| |
| |
| |
Motivation | |
| |
| |
| |
Goals of Learning | |
| |
| |
| |
Learning as Optimization | |
| |
| |
| |
Learning Tasks | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Parameter Estimation | |
| |
| |
| |
Maximum Likelihood Estimation | |
| |
| |
| |
MLE for Bayesian Networks | |
| |
| |
| |
Bayesian Parameter Estimation | |
| |
| |
| |
Bayesian Parameter Estimation in Bayesian Networks | |
| |
| |
| |
Learning Models with Shared Parameters | |
| |
| |
| |
Generalization Analysis | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Structure Learning in Bayesian Networks | |
| |
| |
| |
Introduction | |
| |
| |
| |
Constraint-Based Approaches | |
| |
| |
| |
Structure Scores | |
| |
| |
| |
Structure Search | |
| |
| |
| |
Bayesian Model Averaging | |
| |
| |
| |
Learning Models with Additional Structure | |
| |
| |
| |
Summary and Discussion | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Partially Observed Data | |
| |
| |
| |
Foundations | |
| |
| |
| |
Parameter Estimation | |
| |
| |
| |
Bayesian Learning with Incomplete Data | |
| |
| |
| |
Structure Learning | |
| |
| |
| |
Learning Models with Hidden Variables | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Learning Undirected Models | |
| |
| |
| |
Overview | |
| |
| |
| |
The Likelihood Function | |
| |
| |
| |
Maximum (Conditional) Likelihood Parameter Estimation | |
| |
| |
| |
Parameter Priors and Regularization | |
| |
| |
| |
Learning with Approximate Inference | |
| |
| |
| |
Alternative Objectives | |
| |
| |
| |
Structure Learning | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Actions and Decisions | |
| |
| |
| |
Causality | |
| |
| |
| |
Motivation and Overview | |
| |
| |
| |
Causal Models | |
| |
| |
| |
Structural Causal Identifiability | |
| |
| |
| |
Mechanisms and Response Variables | |
| |
| |
| |
Partial Identifiability in Functional Causal Models | |
| |
| |
| |
Counterfactual Queries | |
| |
| |
| |
Learning Causal Models | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Utilities and Decisions | |
| |
| |
| |
Foundations: Maximizing Expected Utility | |
| |
| |
| |
Utility Curves | |
| |
| |
| |
Utility Elicitation | |
| |
| |
| |
Utilities of Complex Outcomes | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Structured Decision Problems | |
| |
| |
| |
Decision Trees | |
| |
| |
| |
Influence Diagrams | |
| |
| |
| |
Backward Induction in Influence Diagrams | |
| |
| |
| |
Computing Expected Utilities | |
| |
| |
| |
Optimization in Influence Diagrams | |
| |
| |
| |
Ignoring Irrelevant Information | |
| |
| |
| |
Value of Information | |
| |
| |
| |
Summary | |
| |
| |
| |
Relevant Literature | |
| |
| |
| |
Exercises | |
| |
| |
| |
Epilogue | |
| |
| |
| |
Background Material | |
| |
| |
| |
Information Theory | |
| |
| |
| |
Convergence Bounds | |
| |
| |
| |
Algorithms and Algorithmic Complexity | |
| |
| |
| |
Combinatorial Optimization and Search | |
| |
| |
| |
Continuous Optimization | |
| |
| |
Bibliography | |
| |
| |
Notation Index | |
| |
| |
Subject Index | |